claudio.cool

⚠ New certification: Anthropic published its guide (version 1.0, November 2026) on 17 November 2026. The lessons and questions are a first draft built on that guide and will be refined.

CCDV-P

Claude Certified Developer (Professional)

Who it is for: Senior engineers who run Claude applications and agents in production: reliability, quality, cost, security, and fleets of coding agents.

70 questions · 120 minutes

25 lessons · 8 domains

Take a practice exam
How do I take the exam?
  1. Your company must be part of the Claude Partner Network. Joining is free. If it is not yet, sign up for Kelsoft’s Anthropic Challenge and ask Cande.
  2. On the Anthropic Partner Academy, open the certification page, read the guide and the terms, and register. The list price is USD 175; checkout shows the final price, with any discount for your company's partner tier.
  3. On the Academy, choose Register and confirm your name matches your government-issued ID. You then go straight to Pearson, already signed in, to schedule and pay: online proctored or at a Pearson test centre. If you were already registered, do not register again: use “Go to my Pearson account” instead.
  4. You can cancel or reschedule up to 24 hours before. After that, the fee is forfeited.
  5. The credential lasts 12 months. Renewing on time is free: a short, non-proctored assessment on what has changed.
Go to the Anthropic Partner Academy ↗

Mocks

70 questions, 120 minutes, a mix of all domains, scored out of 1000.

  1. Mock 1Not takenStart
  2. Mock 2Not takenStart
  3. Mock 3Not takenStart
  4. Mock 4Not takenStart
  5. Mock 5Not takenStart
Review list: 0 questions you missed or flagged

Questions you miss or flag in the mocks will show up here so you can review them.

Your preparation

Diagnostic

You haven't taken it yet. See where you stand in each domain.

Take the diagnostic Timed diagnostic (account required)

Lessons

0 of 25 read

Next: Multi-agent patterns in production and how they fail at the seams

Drill

Series of 15 questions aimed at one domain.

Once you take the diagnostic, we'll suggest the domain that's best to practice.

Start a drill

Domains

Advanced Agent Architecture and Orchestration 17%

  1. Multi-agent patterns in production and how they fail at the seams
  2. Durable execution, checkpoints, sessions and resumability
  3. Evolving between workflow and agent with data, and setting harness and framework standards
  4. Context and memory policies for long-running agents
Practice exam →

Production Integration, Reliability, and Knowledge Grounding 20%

  1. Reliability, retries, circuit breakers and fallbacks that tell causes apart
  2. Scale and throughput, finding the binding constraint
  3. MCP in production and model or prompt changes without surprises
  4. Retrieval and grounding, diagnosing by stage and not making things up
Practice exam →

Observability and Production Monitoring 12%

  1. What to instrument in a Claude system, and what not to store
  2. SLIs, SLOs, alerting and quality drift
  3. Trace analysis at scale, sampling, aggregation and failure cohorts
Practice exam →

Advanced Debugging and Incident Response 10%

  1. Isolating where a failure originates, model, harness, tools or data
  2. Incidents, mitigate first and turn the learning into evaluations
Practice exam →

Evaluation Engineering and Quality Assurance 12%

  1. Designing the evaluation system, golden sets, regression and release gates
  2. An LLM judge must be calibrated, rubrics, biases and agreement with people
  3. Measuring quality on live traffic, sampling, A/B tests and feedback
Practice exam →

Cost and Latency Optimization at Scale 8%

  1. Cost architecture, model, route, cache and cap
  2. Latency engineering, first token or total, and what to move
Practice exam →

Runtime Guardrails and Production Security 11%

  1. Runtime guardrails, layers, hooks and keeping the irreversible outside the model
  2. Agents facing untrusted content, the dangerous combination and defense in depth
  3. Agent identity, secrets without static keys and audit
Practice exam →

Agent Fleet Operations for Software Delivery 10%

  1. Parallel agents, worktrees, decomposition and merge strategy
  2. When generation outpaces review, AI code review in shadow mode
  3. Agents with nobody watching, goals, schedules and event response
  4. Configuring coding agents across the whole organization
Practice exam →